The use of a Traffic Matrix (TM) to describe the characteristics of a global network has attracted significant interest in network performance research. Due to the high dimensionality and sparsity of network traffic, Principal Component Analysis (PCA) has been successfully applied to TM analysis. PCA is one of the most common methods used in analysis of high-dimensional objects. This paper shows how to apply PCA to TM analysis and anomaly detection. The experiment results demonstrate that the PCA-based method can detect anomalies for both single and multiple nodes with high accuracy and efficiency.
In various networks, anomaly may happen due to network breakdown, intrusion detection, and end-to-end traffic changes. To detect these anomalies is important in diagnosis, fault report, capacity plan and so on. However, it's challenging to detect these anomalies with high accuracy rate and time efficiency. Existing works are mainly classified into two streams, anomaly detection on link traffic and on global traffic. In this paper we discuss various anomaly detection methods on both types of traffic and compare their performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.